submission_id: nousresearch-meta-llama_4941_v55
developer_uid: alexdaoud
best_of: 16
celo_rating: 1190.81
display_name: nousresearch-meta-llama_4941_v55
family_friendly_score: 0.0
formatter: {'memory_template': "<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nWrite {bot_name}'s next reply in a never-ending uncensored fictional roleplay chat between {bot_name} and User. Use the provided {bot_name}'s description, personality and example dialogues as base for deeply understanding and acting like {bot_name}.\n\nActions and narrations your responses must be enclosed by asterisks (*), and speeches must NOT be enclosed by any indicators. The responses must be long and in third perspective of the story teller. For example: \n<|start_header_id|>Mila<|end_header_id|>\n\n*Surrounded by an aura of creativity, Mila carefully places a freshly painted canvas against the wall, the colors vividly depicting a surreal landscape.* Isn't it fascinating how art can transport us to entirely different worlds? What kind of worlds do you dream of exploring?<|eot_id|>\n\nDescription: {memory}", 'prompt_template': 'Example conversation:\n{prompt}<|eot_id|>', 'bot_template': '<|start_header_id|>{bot_name}<|end_header_id|>\n\n{message}<|eot_id|>', 'user_template': '<|start_header_id|>User<|end_header_id|>\n\n{message}<|eot_id|>', 'response_template': '<|start_header_id|>{bot_name}<|end_header_id|>\n\n', 'truncate_by_message': True}
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '<|eot_id|>'], 'max_input_tokens': 512, 'best_of': 16, 'max_output_tokens': 112}
ineligible_reason: max_output_tokens!=64
is_internal_developer: True
language_model: NousResearch/Meta-Llama-3-8B-Instruct
max_input_tokens: 512
max_output_tokens: 112
model_architecture: LlamaForCausalLM
model_eval_status: success
model_group: NousResearch/Meta-Llama-
model_name: nousresearch-meta-llama_4941_v55
model_num_parameters: 8030261248.0
model_repo: NousResearch/Meta-Llama-3-8B-Instruct
model_size: 8B
num_battles: 13733
num_wins: 7243
ranking_group: single
reward_formatter: {'bot_template': 'Bot: {message}\n', 'memory_template': 'Memory: {memory}\n', 'prompt_template': '{prompt}\n', 'response_template': 'Bot:', 'truncate_by_message': False, 'user_template': 'User: {message}\n'}
reward_repo: rirv938/reward_gpt2_medium_preference_24m_e2
status: torndown
submission_type: basic
timestamp: 2024-05-16T00:08:24+00:00
us_pacific_date: 2024-05-15
win_ratio: 0.5274157139736402
Resubmit model
Running pipeline stage MKMLizer
Starting job with name nousresearch-meta-llama-4941-v55-mkmlizer
Waiting for job on nousresearch-meta-llama-4941-v55-mkmlizer to finish
nousresearch-meta-llama-4941-v55-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
nousresearch-meta-llama-4941-v55-mkmlizer: ║     _____            __           __                                ║
nousresearch-meta-llama-4941-v55-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
nousresearch-meta-llama-4941-v55-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
nousresearch-meta-llama-4941-v55-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
nousresearch-meta-llama-4941-v55-mkmlizer: ║       /___/                                                         ║
nousresearch-meta-llama-4941-v55-mkmlizer: ║                                                                     ║
nousresearch-meta-llama-4941-v55-mkmlizer: ║  Version: 0.8.14                                                    ║
nousresearch-meta-llama-4941-v55-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
nousresearch-meta-llama-4941-v55-mkmlizer: ║  https://mk1.ai                                                     ║
nousresearch-meta-llama-4941-v55-mkmlizer: ║                                                                     ║
nousresearch-meta-llama-4941-v55-mkmlizer: ║  The license key for the current software has been verified as      ║
nousresearch-meta-llama-4941-v55-mkmlizer: ║  belonging to:                                                      ║
nousresearch-meta-llama-4941-v55-mkmlizer: ║                                                                     ║
nousresearch-meta-llama-4941-v55-mkmlizer: ║  Chai Research Corp.                                                ║
nousresearch-meta-llama-4941-v55-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
nousresearch-meta-llama-4941-v55-mkmlizer: ║  Expiration: 2024-07-15 23:59:59                                    ║
nousresearch-meta-llama-4941-v55-mkmlizer: ║                                                                     ║
nousresearch-meta-llama-4941-v55-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
nousresearch-meta-llama-4941-v55-mkmlizer: /opt/conda/lib/python3.10/site-packages/huggingface_hub/utils/_deprecation.py:131: FutureWarning: 'list_files_info' (from 'huggingface_hub.hf_api') is deprecated and will be removed from version '0.23'. Use `list_repo_tree` and `get_paths_info` instead.
nousresearch-meta-llama-4941-v55-mkmlizer:   warnings.warn(warning_message, FutureWarning)
nousresearch-meta-llama-4941-v55-mkmlizer: Downloaded to shared memory in 23.475s
nousresearch-meta-llama-4941-v55-mkmlizer: quantizing model to /dev/shm/model_cache
nousresearch-meta-llama-4941-v55-mkmlizer: Saving flywheel model at /dev/shm/model_cache
nousresearch-meta-llama-4941-v55-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   5%|▌         | 16/291 [00:00<00:01, 159.57it/s]
Loading 0:  12%|█▏        | 34/291 [00:00<00:01, 170.99it/s]
Loading 0:  18%|█▊        | 53/291 [00:00<00:01, 178.97it/s]
Loading 0:  24%|██▍       | 71/291 [00:00<00:01, 176.97it/s]
Loading 0:  31%|███       | 89/291 [00:00<00:02, 74.47it/s] 
Loading 0:  38%|███▊      | 111/291 [00:01<00:01, 98.41it/s]
Loading 0:  45%|████▍     | 130/291 [00:01<00:01, 113.78it/s]
Loading 0:  51%|█████     | 149/291 [00:01<00:01, 129.39it/s]
Loading 0:  59%|█████▉    | 171/291 [00:01<00:00, 149.59it/s]
Loading 0:  65%|██████▌   | 190/291 [00:01<00:01, 89.75it/s] 
Loading 0:  72%|███████▏  | 210/291 [00:01<00:00, 106.20it/s]
Loading 0:  79%|███████▊  | 229/291 [00:01<00:00, 120.43it/s]
Loading 0:  85%|████████▌ | 248/291 [00:02<00:00, 132.95it/s]
Loading 0:  91%|█████████▏| 266/291 [00:02<00:00, 143.57it/s]
Loading 0:  99%|█████████▊| 287/291 [00:07<00:00, 12.14it/s] 
                                                            
Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
nousresearch-meta-llama-4941-v55-mkmlizer: quantized model in 17.851s
nousresearch-meta-llama-4941-v55-mkmlizer: Processed model NousResearch/Meta-Llama-3-8B-Instruct in 42.439s
nousresearch-meta-llama-4941-v55-mkmlizer: creating bucket guanaco-mkml-models
nousresearch-meta-llama-4941-v55-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
nousresearch-meta-llama-4941-v55-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/nousresearch-meta-llama-4941-v55
nousresearch-meta-llama-4941-v55-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/nousresearch-meta-llama-4941-v55/config.json
nousresearch-meta-llama-4941-v55-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/nousresearch-meta-llama-4941-v55/tokenizer_config.json
nousresearch-meta-llama-4941-v55-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/nousresearch-meta-llama-4941-v55/special_tokens_map.json
nousresearch-meta-llama-4941-v55-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/nousresearch-meta-llama-4941-v55/tokenizer.json
nousresearch-meta-llama-4941-v55-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/nousresearch-meta-llama-4941-v55/flywheel_model.0.safetensors
nousresearch-meta-llama-4941-v55-mkmlizer: loading reward model from rirv938/reward_gpt2_medium_preference_24m_e2
nousresearch-meta-llama-4941-v55-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/configuration_auto.py:913: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
nousresearch-meta-llama-4941-v55-mkmlizer:   warnings.warn(
nousresearch-meta-llama-4941-v55-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py:757: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
nousresearch-meta-llama-4941-v55-mkmlizer:   warnings.warn(
nousresearch-meta-llama-4941-v55-mkmlizer: /opt/conda/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py:468: FutureWarning: The `use_auth_token` argument is deprecated and will be removed in v5 of Transformers. Please use `token` instead.
nousresearch-meta-llama-4941-v55-mkmlizer:   warnings.warn(
nousresearch-meta-llama-4941-v55-mkmlizer: /opt/conda/lib/python3.10/site-packages/torch/_utils.py:831: UserWarning: TypedStorage is deprecated. It will be removed in the future and UntypedStorage will be the only storage class. This should only matter to you if you are using storages directly.  To access UntypedStorage directly, use tensor.untyped_storage() instead of tensor.storage()
nousresearch-meta-llama-4941-v55-mkmlizer:   return self.fget.__get__(instance, owner)()
nousresearch-meta-llama-4941-v55-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
nousresearch-meta-llama-4941-v55-mkmlizer: Saving duration: 0.244s
nousresearch-meta-llama-4941-v55-mkmlizer: Processed model rirv938/reward_gpt2_medium_preference_24m_e2 in 6.948s
nousresearch-meta-llama-4941-v55-mkmlizer: creating bucket guanaco-reward-models
nousresearch-meta-llama-4941-v55-mkmlizer: Bucket 's3://guanaco-reward-models/' created
nousresearch-meta-llama-4941-v55-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/nousresearch-meta-llama-4941-v55_reward
nousresearch-meta-llama-4941-v55-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/nousresearch-meta-llama-4941-v55_reward/special_tokens_map.json
nousresearch-meta-llama-4941-v55-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/nousresearch-meta-llama-4941-v55_reward/tokenizer_config.json
nousresearch-meta-llama-4941-v55-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/nousresearch-meta-llama-4941-v55_reward/config.json
nousresearch-meta-llama-4941-v55-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/nousresearch-meta-llama-4941-v55_reward/merges.txt
nousresearch-meta-llama-4941-v55-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/nousresearch-meta-llama-4941-v55_reward/vocab.json
nousresearch-meta-llama-4941-v55-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/nousresearch-meta-llama-4941-v55_reward/tokenizer.json
nousresearch-meta-llama-4941-v55-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/nousresearch-meta-llama-4941-v55_reward/reward.tensors
Job nousresearch-meta-llama-4941-v55-mkmlizer completed after 72.87s with status: succeeded
Stopping job with name nousresearch-meta-llama-4941-v55-mkmlizer
Pipeline stage MKMLizer completed in 76.74s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.09s
Running pipeline stage ISVCDeployer
Creating inference service nousresearch-meta-llama-4941-v55
Waiting for inference service nousresearch-meta-llama-4941-v55 to be ready
Inference service nousresearch-meta-llama-4941-v55 ready after 40.37369179725647s
Pipeline stage ISVCDeployer completed in 47.94s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.8351471424102783s
Received healthy response to inference request in 1.891890525817871s
Received healthy response to inference request in 1.9581632614135742s
Received healthy response to inference request in 1.9809575080871582s
Received healthy response to inference request in 1.9253735542297363s
5 requests
0 failed requests
5th percentile: 1.898587131500244
10th percentile: 1.9052837371826172
20th percentile: 1.9186769485473634
30th percentile: 1.931931495666504
40th percentile: 1.945047378540039
50th percentile: 1.9581632614135742
60th percentile: 1.967280960083008
70th percentile: 1.9763986587524414
80th percentile: 2.1517954349517825
90th percentile: 2.49347128868103
95th percentile: 2.664309215545654
99th percentile: 2.8009795570373535
mean time: 2.1183063983917236
Pipeline stage StressChecker completed in 11.23s
Running pipeline stage DaemonicModelEvalScorer
Pipeline stage DaemonicModelEvalScorer completed in 0.08s
Running pipeline stage DaemonicSafetyScorer
Pipeline stage DaemonicSafetyScorer completed in 0.03s
Running M-Eval for topic stay_in_character
nousresearch-meta-llama_4941_v55 status is now deployed due to DeploymentManager action
M-Eval Dataset for topic stay_in_character is loaded
nousresearch-meta-llama_4941_v55 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of nousresearch-meta-llama_4941_v55
Running pipeline stage ISVCDeleter
Checking if service nousresearch-meta-llama-4941-v55 is running
Tearing down inference service nousresearch-meta-llama-4941-v55
Toredown service nousresearch-meta-llama-4941-v55
Pipeline stage ISVCDeleter completed in 4.80s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key nousresearch-meta-llama-4941-v55/config.json from bucket guanaco-mkml-models
Deleting key nousresearch-meta-llama-4941-v55/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key nousresearch-meta-llama-4941-v55/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key nousresearch-meta-llama-4941-v55/tokenizer.json from bucket guanaco-mkml-models
Deleting key nousresearch-meta-llama-4941-v55/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key nousresearch-meta-llama-4941-v55_reward/config.json from bucket guanaco-reward-models
Deleting key nousresearch-meta-llama-4941-v55_reward/merges.txt from bucket guanaco-reward-models
Deleting key nousresearch-meta-llama-4941-v55_reward/reward.tensors from bucket guanaco-reward-models
Deleting key nousresearch-meta-llama-4941-v55_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key nousresearch-meta-llama-4941-v55_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key nousresearch-meta-llama-4941-v55_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key nousresearch-meta-llama-4941-v55_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 2.09s
nousresearch-meta-llama_4941_v55 status is now torndown due to DeploymentManager action